SYSTEMS AND METHODS FOR DISTRIBUTING REPLICATION TASKS WITHIN COMPUTING CLUSTERS

• US 20140279884A1
• Filed: 04/04/2013
• Published: 09/18/2014
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Veritas Technologies, LLC (Whitehouse Group Ltd.)
• Original Assignee: Symantec Corporation (NortonLifeLock Inc.)
• Inventors: Raut, Yojana, Dantkale, Suhas
• Granted Patent: US 9,075,856 B2
• Time in Patent Office: Days
• US Class Current: 707/620
• CPC Class Codes: G06F 16/182 Distributed file systems
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor

Abstract

A computer-implemented method for distributing replication tasks within computing clusters may include (1) identifying a primary volume that is replicated to a secondary volume, (2) identifying a computing cluster with access to the primary volume that includes at least a first node and a second node, (3) receiving a request to write data to the primary volume, (4) logging, via the first node, the request to write the data to the primary volume to a replication log, and (5) using the replication log to replicate, via the second node, the data to the secondary volume. Various other methods, systems, and computer-readable media are also disclosed.

Claims

1. A computer-implemented method for distributing replication tasks within computing clusters, at least a portion of the method being performed by a computing device comprising at least one processor, the method comprising:

identifying a primary volume that is replicated to a secondary volume;

identifying a computing cluster with access to the primary volume, the computing cluster comprising at least a first node and a second node;

receiving a request to write data to the primary volume;

logging, via the first node, the request to write the data to the primary volume to a replication log;

using the replication log to replicate, via the second node, the data to the secondary volume.

2. The computer-implemented method of claim 1, wherein only one node within the computing cluster is capable of having read/write access to the replication log;

further comprising, prior to receiving the request to write the data to the primary volume;

configuring the first node with read/write access to the replication log;

configuring the second node with read-only access to the replication log.

3. The computer-implemented method of claim 1, wherein:

the second node is configured with read-only access to the replication log;

using the replication log to replicate, via the second node, the data to the secondary volume comprises;

reading, at the second node, the data from the replication log;

replicating, via the second node, the data to the secondary volume;

receiving, at the second node, a notification that indicates that the data has been successfully replicated to the secondary volume;

sending, via the second node, a request to the first node that instructs the first node to update the replication log to reflect the data having been successfully replicated to the secondary volume.

4. The computer-implemented method of claim 1, wherein more than one node within the computing cluster is capable of having read/write access to the replication log;

further comprising configuring, prior to receiving the request to write the data to the primary volume, the first node and the second node with read/write access to the replication log.

5. The computer-implemented method of claim 1, wherein logging, via the first node, the request to write the data to the primary volume to the replication log comprises:

allocating, at the first node, a position in the replication log to which the request to write the data to the primary volume can be logged;

logging the request to write the data to the primary volume to the position in the replication log.

6. The computer-implemented method of claim 1, wherein using the replication log to replicate, via the second node, the data to the secondary volume comprises:

reading, at the second node, the data from the replication log;

replicating, via the second node, the data to the secondary volume;

receiving, at the second node, a notification that indicates that the data has been successfully replicated to the secondary volume;

updating, at the second node, the replication log to reflect the data having been successfully replicated to the secondary volume.

7. The computer-implemented method of claim 1, further comprising, prior to receiving the request to write the data to the primary volume:

monitoring the input/output load on the first node;

determining that the input/output load on the first node is greater than the input/output load on any other node in the computing cluster;

selecting, based at least in part on determining that the input/output load of the first node is greater than the input/output load of any other node in the computing cluster, the first node to log the request to write the data to the primary volume to the replication log.

8. The computer-implemented method of claim 1, further comprising, prior to receiving the request to write the data to the primary volume:

monitoring at least one property of the computing cluster;

selecting, based at least in part on the property of the computing cluster, the second node to use the replication log to replicate the data to the secondary volume.

9. The computer-implemented method of claim 8, wherein the property of the computing cluster comprises at least one of:

the input/output load on the second node;

central-processing-unit availability on the second node;

memory availability on the second node;

network-bandwidth availability on the second node;

whether the second node has access to the replication log;

whether the second node has access to a network interface required to replicate the primary volume to the secondary volume.

10. The computer-implemented method of claim 1, further comprising failing over, to an additional node within the computing cluster, at least one replication task associated with replicating the primary volume to the secondary volume.

11. The computer-implemented method of claim 1, wherein the first node is distinct from the second node.

12. A system for distributing replication tasks within computing clusters, the system comprising:

an identifying module programmed to;

identify a primary volume that is replicated to a secondary volume;

identify a computing cluster with access to the primary volume, the computing cluster comprising at least a first node and a second node;

a receiving module programmed to receive a request to write data to the primary volume;

a logging module programmed to log, via the first node, the request to write the data to the primary volume to a replication log;

a replicating module programmed to use the replication log to replicate, via the second node, the data to the secondary volume;

at least one processor configured to execute the identifying module, the receiving module, the logging module, and the replicating module.

13. The system of claim 12, wherein only one node within the computing cluster is capable of having read/write access to the replication log;

further comprising a configuring module programmed to, prior to receiving the request to write the data to the primary volume;

configure the first node with read/write access to the replication log;

configure the second node with read-only access to the replication log.

14. The system of claim 12, wherein:

the second node is configured with read-only access to the replication log;

the replicating module is programmed to use the replication log to replicate, via the second node, the data to the secondary volume by;

reading, at the second node, the data from the replication log;

replicating, via the second node, the data to the secondary volume;

receiving, at the second node, a notification that indicates that the data has been successfully replicated to the secondary volume;

sending, via the second node, a request to the first node that instructs the first node to update the replication log to reflect the data having been successfully replicated to the secondary volume.

15. The system of claim 12, wherein more than one node within the computing cluster is capable of having read/write access to the replication log;

further comprising a configuring module programmed to configure, prior to receiving the request to write the data to the primary volume, the first node and the second node with read/write access to the replication log.

16. The system of claim 12, wherein the logging module is programmed to log, via the first node, the request to write the data to the primary volume to the replication log by:

allocating, at the first node, a position in the replication log to which the request to write the data to the primary volume can be logged;

logging the request to write the data to the primary volume to the position in the replication log.

17. The system of claim 12, wherein the replicating module is programmed to use the replication log to replicate, via the second node, the data to the secondary volume by:

reading, at the second node, the data from the replication log;

replicating, via the second node, the data to the secondary volume;

receiving, at the second node, a notification that indicates that the data has been successfully replicated to the secondary volume;

updating, at the second node, the replication log to reflect the data having been successfully replicated to the secondary volume.

18. The system of claim 12, further comprising a configuring module programmed to, prior to receiving the request to write the data to the primary volume:

monitor the input/output load on the first node;

determine that the input/output load on the first node is greater than the input/output load on any other node in the computing cluster;

select, based at least in part on determining that the input/output load of the first node is greater than the input/output load of any other node in the computing cluster, the first node to log the request to write the data to the primary volume to the replication log.

19. The system of claim 12, further comprising a configuring module programmed to, prior to receiving the request to write the data to the primary volume:

monitor at least one property of the computing cluster;

select, based at least in part on the property of the computing cluster, the second node to use the replication log to replicate the data to the secondary volume.

20. A non-transitory computer-readable medium comprising one or more computer-executable instructions that, when executed by at least one processor of a computing device, cause the computing device to:

identify a primary volume that is replicated to a secondary volume;

identify a computing cluster with access to the primary volume, the computing cluster comprising at least a first node and a second node;

receive a request to write data to the primary volume;

log, via the first node, the request to write the data to the primary volume to a replication log;

use the replication log to replicate, via the second node, the data to the secondary volume.